{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T12:51:30Z","timestamp":1776516690920,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889731","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing 3D Medical Image Understanding with 2D Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Qiuhui","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuancheng","family":"Yao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huping","family":"Ye","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Hong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"M3d: Advancing 3d medical image analysis with multi-modal large language models","author":"Bai","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002699"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","article-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_6"},{"key":"ref7","article-title":"Med3d: Transfer learning for 3d medical image analysis","author":"Chen","year":"2019"},{"key":"ref8","article-title":"Generative text-guided 3d vision-language pretraining for unified medical image segmentation","author":"Chen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00201"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_58"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","article-title":"Densenet: Implementing efficient convnet descriptor pyramids","author":"Iandola","year":"2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1117\/12.2293725"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101950"},{"key":"ref19","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref20","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on machine learning","author":"Li"},{"key":"ref21","article-title":"T3d: Towards 3d medical image understanding through vision-language pre-training","author":"Liu","year":"2023"},{"key":"ref22","first-page":"36","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2009.21407"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2007.19.9.1498"},{"key":"ref26","article-title":"Attention u-net: Learning where to look for the pancreas","author":"Oktay","year":"2018"},{"key":"ref27","year":"2023","journal-title":"OpenAI: Gpt-4v(ision) system card"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref32","article-title":"Can gpt-4v (ision) serve medical applications? case studies on gpt-4v for multimodal medical diagnosis","author":"Wu","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref34","first-page":"2023","article-title":"Performance of multimodal gpt-4v on usmle with image: Potential for imaging diagnostic support with explanations","author":"Yang","year":"2023","journal-title":"medRxiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293771"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234002"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230477"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3688863.3689575"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.02.006"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889731.pdf?arnumber=10889731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:32Z","timestamp":1774416212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889731","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}